Webforai Text Extractor

🚀 WebforAI Text Extractor - MCP Server

This is a Model Context Protocol (MCP) server based on Cloudflare Workers that uses WebforAI to extract plain text from web pages.

🌟 What is WebforAI?

WebforAI is a powerful library designed to make web content accessible and usable for AI models. It provides the following tools:

• Convert HTML to clean, structured Markdown
• Extract meaningful content from web pages
• Intelligently handle tables, links, and images
• Prepare web content for consumption by AI

This MCP server leverages the capabilities of WebforAI to extract plain text from any web page URL, allowing you to easily input web content into AI models via the Model Context Protocol (MCP).

✨ Features

• Simple API: Extract text from any web page with a single API call.
• Clean Output: Receive well - formatted Markdown text without HTML noise.
• Error Handling: Robustly handle failed requests.
• Cloudflare Workers: Serverless deployment with global distribution.
• MCP Compatible: Compatible with any MCP client, such as Claude Desktop or Cloudflare AI Playground.

🚀 Quick Start

Deploy to Cloudflare Workers

This will deploy your MCP server to a URL like webforai-mcp-server.<your-account>.workers.dev/sse.

Local Development

1. Clone this repository:

   git clone https://github.com/yutakobayashidev/webforai-mcp-server.git
   cd webforai-mcp-server
   

2. Install dependencies:

   pnpm install
   

3. Start the development server:

   pnpm dev
   

4. Your server will be available at http://localhost:8787.

💻 Usage Examples

Basic Usage

extractWebPageText tool accepts a web page URL and returns the extracted text content in Markdown format:

{
  "url": "https://example.com/page"
}

The response will contain well - formatted Markdown text where:

• Links are converted to plain text.
• Tables are converted to plain text.
• Images are hidden.

🔌 Connect to MCP Clients

Cloudflare AI Playground

1. Visit Cloudflare AI Playground.
2. Enter the URL of your deployed MCP server (webforai-mcp-server.<your-account>.workers.dev/sse).
3. Now, you can use the text extraction tool directly from the playground!

Claude Desktop

To connect to your MCP server from Claude Desktop:

1. Follow Anthropic's Quick Start Guide.
2. In Claude Desktop, go to Settings > Developers > Edit Configuration.
3. Update with the following configuration:

{
  "mcpServers": {
    "webforaiExtractor": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/sse"  // or webforai-mcp-server.your-account.workers.dev/sse
      ]
    }
  }
}

4. Restart Claude, and you should see the text extraction tool become available.

📚 Documentation

• WebforAI Documentation
• Model Context Protocol
• Cloudflare Workers
• Cloudflare AI

📄 License

MIT